The Study for Data Mining of Distribution Network Based on Particle Swarm Optimization with Clustering Algorithm Method

Abstract

In the field of distribution network information system, the research on fault data sorting of feeder is an important subject. The data needed from feeder line can be extracted to lay a foundation for fault prediction. Since the quality of the raw data may be problematic, this paper proposes a method of outlier detection based on clustering. In the method, particle swarm optimization algorithm is used to optimize the clustering center and optimal number of clusters is determined by K-means method. This method can effectively promote the clustering effect, accurately remove the outlier samples and escape from the negative impact on the prediction model caused by the outlier samples. Simulation results show that this method can get good data from fault sorting of feeder, which provides a new idea for distribution network information sorting.